To Christian Posta <https://www.mail-archive.com/search?l=d...@kafka.apache.org&q=from:%22Christian+Posta%22>, I have taken into account the interpretation of time. my producer and consumer are deployed on the same machine, the machine’s configuration is very good, so it will not be the bottlenecks. so it’s not have the problem of interpretation of time.
> 在 2016年6月18日，上午11:26，Kafka <kafka...@126.com> 写道： > > hello，I have done a series of tests on kafka 0.9.0，and one of the results > confused me. > > test enviroment: > kafka cluster: 3 brokers，8core cpu ／ 8g mem ／1g netcard > client：4core cpu／4g mem > topic：6 partitions，2 replica > > total messages：10000 > singal message size：1024byte > fetch.min.bytes:1 > fetch.wait.max.ms:100ms > > all send tests are under the enviroment of using scala sync interface， > > when I set ack to 0，the producer’s delay is 0.3ms，the consumer’s delay is > 7.7ms > when I set ack to 1，the producer's delay is 1.6ms, the consumer’s delay is > 3.7ms > when I set ack to -1，the produce's delay is 3.5ms, the consumer’s delay is > 4.2ms > > but why consumer’s delay is decreased when I set ack from 0 to 1，its confused > me。 >
